Training in progress, step 10000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1135685
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58691820f476a567a7509aeb201ddbf531c73f311c1fe52ed9507721ad2644cd
|
3 |
size 1135685
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 307910149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dbb7038a0f0645b0d66d337c43e0b2fc42278e08768249e5041d44350bdc159
|
3 |
size 307910149
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4f34ed6fb62f3e32f3b95ab6c580d66c7cd9f7bde80e675435ce41a6bf51932
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71a546360b22b38e65568c028955da704276b3a9551ee9dcac6165cd80d1258c
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.7246909141540527,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-6000",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -94,11 +94,33 @@
|
|
94 |
"eval_samples_per_second": 63.509,
|
95 |
"eval_steps_per_second": 0.994,
|
96 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
97 |
}
|
98 |
],
|
99 |
"max_steps": 85840,
|
100 |
"num_train_epochs": 10,
|
101 |
-
"total_flos": 1.
|
102 |
"trial_name": null,
|
103 |
"trial_params": null
|
104 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.7246909141540527,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-6000",
|
4 |
+
"epoch": 1.1649580615097856,
|
5 |
+
"global_step": 10000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
94 |
"eval_samples_per_second": 63.509,
|
95 |
"eval_steps_per_second": 0.994,
|
96 |
"step": 8000
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 1.16,
|
100 |
+
"learning_rate": 0.0009300044145779173,
|
101 |
+
"loss": 1.2871,
|
102 |
+
"step": 10000
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 1.16,
|
106 |
+
"eval_accuracy": null,
|
107 |
+
"eval_bertscore_f1": 0.9358213962977603,
|
108 |
+
"eval_bleu": 0.4193950275310417,
|
109 |
+
"eval_f1": null,
|
110 |
+
"eval_loss": 1.7429882287979126,
|
111 |
+
"eval_rouge1": 0.6213453720058478,
|
112 |
+
"eval_rouge2": 0.4161815104047649,
|
113 |
+
"eval_rougeL": 0.5663236030411948,
|
114 |
+
"eval_rougeLsum": 0.5683627905966635,
|
115 |
+
"eval_runtime": 166.3727,
|
116 |
+
"eval_samples_per_second": 59.156,
|
117 |
+
"eval_steps_per_second": 0.926,
|
118 |
+
"step": 10000
|
119 |
}
|
120 |
],
|
121 |
"max_steps": 85840,
|
122 |
"num_train_epochs": 10,
|
123 |
+
"total_flos": 1.510371605809152e+16,
|
124 |
"trial_name": null,
|
125 |
"trial_params": null
|
126 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 307910149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dbb7038a0f0645b0d66d337c43e0b2fc42278e08768249e5041d44350bdc159
|
3 |
size 307910149
|